Towards efficient post-training quantization of pre-trained language models
Network quantization has gained increasing attention with the rapid growth of large pre-
trained language models~(PLMs). However, most existing quantization methods for PLMs …
trained language models~(PLMs). However, most existing quantization methods for PLMs …
RUL prediction of wind turbine gearbox bearings based on self-calibration temporal convolutional network
The prediction of the remaining useful life (RUL) of wind turbine gearbox bearings is critical
to avoid catastrophic accidents and minimize downtime. Temporal convolutional network …
to avoid catastrophic accidents and minimize downtime. Temporal convolutional network …
TWD-SFNN: Three-way decisions with a single hidden layer feedforward neural network
Neural networks have a strong self-learning ability and a wide range of applications. The
current neural network models mainly determine the number of hidden layer nodes using …
current neural network models mainly determine the number of hidden layer nodes using …
Model compression of deep neural network architectures for visual pattern recognition: Current status and future directions
Abstract Visual Pattern Recognition Networks (VPRNs) are widely used in various visual
data based applications such as computer vision and edge AI. VPRNs help to enhance a …
data based applications such as computer vision and edge AI. VPRNs help to enhance a …
Hrel: Filter pruning based on high relevance between activation maps and class labels
This paper proposes an Information Bottleneck theory based filter pruning method that uses
a statistical measure called Mutual Information (MI). The MI between filters and class labels …
a statistical measure called Mutual Information (MI). The MI between filters and class labels …
Few shot network compression via cross distillation
Abstract Model compression has been widely adopted to obtain light-weighted deep neural
networks. Most prevalent methods, however, require fine-tuning with sufficient training data …
networks. Most prevalent methods, however, require fine-tuning with sufficient training data …
A novel spatiotemporal prediction approach based on graph convolution neural networks and long short-term memory for money laundering fraud
Money laundering is an act of criminals attempting to cover up the nature and source of their
illegal gains. Large-scale money laundering has a great harm to a country's economy …
illegal gains. Large-scale money laundering has a great harm to a country's economy …
Optimization of the structural complexity of artificial neural network for hardware-driven neuromorphic computing application
This work focuses on the optimization of the structural complexity of a single-layer
feedforward neural network (SLFN) for neuromorphic hardware implementation. The …
feedforward neural network (SLFN) for neuromorphic hardware implementation. The …
Stage-wise magnitude-based pruning for recurrent neural networks
A recurrent neural network (RNN) has shown powerful performance in tackling various
natural language processing (NLP) tasks, resulting in numerous powerful models containing …
natural language processing (NLP) tasks, resulting in numerous powerful models containing …
DART: Domain-adversarial residual-transfer networks for unsupervised cross-domain image classification
The accuracy of deep learning (eg, convolutional neural networks) for an image
classification task critically relies on the amount of labeled training data. Aiming to solve an …
classification task critically relies on the amount of labeled training data. Aiming to solve an …